Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3926 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1710. Min Act: -0.0002

Data Index: 1131455 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1156. Min Act: -0.0002

Data Index: 692814 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1728. Min Act: -0.0002

Data Index: 980161 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1010. Min Act: -0.0001

Data Index: 916713 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1665. Min Act: -0.0001

Data Index: 1254085 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1894. Min Act: -0.0002

Data Index: 452407 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.0848. Min Act: -0.0001

Data Index: 789477 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1157. Min Act: -0.0002

Data Index: 991941 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.2203. Min Act: -0.0002

Data Index: 422062 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1646. Min Act: -0.0001

Data Index: 467722 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1727. Min Act: -0.0002

Data Index: 696975 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1678. Min Act: -0.0001

Data Index: 635248 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.0493. Min Act: -0.0002

Data Index: 1195203 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.0797. Min Act: -0.0001

Data Index: 1004174 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1781. Min Act: -0.0002

Data Index: 179016 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.1331. Min Act: -0.0002

Data Index: 809038 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.0740. Min Act: -0.0002

Data Index: 668265 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.0946. Min Act: -0.0002

Data Index: 470708 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.0524. Min Act: -0.0002

Data Index: 1127174 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.2203. Min Range: -1.2203

Max Act: 1.0791. Min Act: -0.0002

Data Index: 27546 (C4 (Web Text))

Max Activating Token Index: 92